CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

doctor

Diagnose and fix oh-my-codex installation issues

Quality

74%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./plugins/oh-my-codex/skills/doctor/SKILL.md

The canonical home for this skill is doctor in Yeachan-Heo/oh-my-codex

SKILL.md
Quality
Evals
Security

Quality

Content

77%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a highly actionable, well-sequenced diagnostic and remediation procedure with strong validation checkpoints and copy-paste commands. Its weaknesses are verbosity (repeated authorization caveats and dense conditional prose) and total lack of progressive disclosure, with remediation detail inlined that should live in reference files.

Suggestions

Split the "Persistent AGENTS guidance" and symlink-handling procedures into a reference file (e.g. references/agents-repair.md) and keep a concise decision summary in SKILL.md.

Deduplicate the repeated "within the authorized scope" caveats into a single stated rule near the top of the Remediation section.

Convert the long conditional prose paragraphs (install/MCP/Team selector substitutions, merge policy restoration) into a compact table or bulleted decision list.

DimensionReasoningScore

Conciseness

The body assumes Claude's competence (no explanations of npm, symlinks, or basic concepts) and is dense with domain-specific constraints, but it could be tightened: authorization caveats like "within the authorized scope" repeat many times, and the "Persistent AGENTS guidance" section stacks interlocking conditionals into 10+ line prose paragraphs that restate the same points.

3 / 5

Actionability

Fully executable, copy-paste ready commands cover the common cases: `omx doctor` variants, a complete plugin-cache inspection bash block, hook/AGENTS/skill-root inspection commands, and explicit scoped `omx setup` commands with flags, substitution rules, and dry-run previews.

5 / 5

Workflow Clarity

A clear diagnostic -> report -> remediate -> re-verify sequence is present with explicit validation steps (--dry-run previews, rerunning `omx doctor` after repair, verifying AGENTS content/policy/Team/hook state before handoff), feedback loops for error recovery ("If restoration fails, report the remaining changed state and stop with ISSUES FOUND"), and a report-contract checklist.

5 / 5

Progressive Disclosure

Sections are well organized, but the ~135-line body inlines everything, including a lengthy AGENTS remediation procedure that belongs in a separate reference file; the only outward pointers are an external GitHub URL and a `templates/AGENTS.md` path, with no bundle reference files, fitting the some-structure-but-should-be-split anchor.

3 / 5

Total

16

/

20

Passed

Description

57%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific to a named tool and clearly states what the skill does, but it is terse to a fault: no trigger guidance and few natural keyword variations. Adding a "Use when..." clause with common user phrasings would raise completeness and trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. "Use when oh-my-codex fails to install, the plugin is not discovered, or omx/doctor commands report errors."

Include natural user phrasings as trigger terms such as "broken installation", "not working", "setup fails", or "plugin not found".

Optionally enumerate the concrete diagnostic areas covered (plugin cache, hooks, AGENTS.md, skills) to improve specificity.

DimensionReasoningScore

Specificity

"Diagnose and fix oh-my-codex installation issues" names the domain plus exactly two concrete actions ("Diagnose and fix"), matching the 1-2 concrete actions anchor; it is below the level of listing several specific actions with comprehensive coverage.

3 / 5

Completeness

The "what" is clear (diagnose and fix installation issues for a named tool), but there is no "Use when..." clause or equivalent explicit trigger guidance, which caps completeness at 3 per the judging guidelines.

3 / 5

Trigger Term Quality

Relevant keywords are present ("diagnose", "fix", "installation issues", "oh-my-codex") but common natural variations users would say (e.g. "broken", "not working", "setup fails", "omx doctor") are missing, fitting the some-relevant-keywords-but-missing-synonyms anchor.

3 / 5

Distinctiveness Conflict Risk

"oh-my-codex" is a unique named tool, giving the description a clear niche with distinct triggers and minimal conflict risk with other skills.

5 / 5

Total

14

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

Yeachan-Heo/oh-my-codex

Path

plugins/oh-my-codex/skills/doctor/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.